Leveraging Domain Knowledge for Reinforcement Learning Using MMC Architectures

Ramamurthy, Rajkumar; Bauckhage, Christian; Sifa, Rafet; Schücker, Jannis; Wrobel, Stefan

doi:10.1007/978-3-030-30484-3_48

Cited by 12 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scientific Knowledge. We observed that algebraic equations are used in machine learning in various domains of natural sciences and engineering, particularly in physics [12], [13], [33], [34], [35], but also in biology [36], [37], robotics [38], or manufacturing and production processes [34], [39].…”

Section: Insert 1: Knowledge-based Loss Termmentioning

confidence: 99%

See 1 more Smart Citation

Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems

Rueden¹,

Mayer²,

Beckh³

et al. 2021

IEEE Trans. Knowl. Data Eng.

Self Cite

388

210

View full text Add to dashboard Cite

Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning.In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.

show abstract

Section: Insert 1: Knowledge-based Loss Termmentioning

confidence: 99%

“…One idea is to sequence predefined operations leading to a functional decomposition [40]. More specifically, relations between input parameters, intermediate observables, or output variables reflecting physical constraints can be encoded as linear connections between the layers of a network model [34], [38].…”

Section: (Paths To) Knowledge Integrationmentioning

confidence: 99%

Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems

Rueden¹,

Mayer²,

Beckh³

et al. 2021

IEEE Trans. Knowl. Data Eng.

Self Cite

388

210

View full text Add to dashboard Cite

show abstract

“…Even as early as [21] the benefits of exploiting additional domain knowledge have been studied. In the literature, the introduction of domain knowledge is typically done by means of reward shaping [22]- [25].…”

Section: A Robotic Information Gathering With Reinforcement Learningmentioning

confidence: 99%

Robotic Information Gathering With Reinforcement Learning Assisted by Domain Knowledge: An Application to Gas Source Localization

et al. 2021

View full text Add to dashboard Cite

Gas source localization tackles the problem of finding leakages of hazardous substances such as poisonous gases or radiation in the event of a disaster. In order to avoid threats for human operators, autonomous robots dispatched for localizing potential gas sources are preferable. This work investigates a Reinforcement Learning framework that allows a robotic agent to learn how to localize gas sources. We propose a solution that assists Reinforcement Learning with existing domain knowledge based on a model of the gas dispersion process. In particular, we incorporate a priori domain knowledge by designing appropriate rewards and observation inputs for the Reinforcement Learning algorithm. We show that a robot trained with our proposed method outperforms state-of-the-art gas source localization strategies, as well as robots that are trained without additional domain knowledge. Furthermore, the framework developed in this work can also be generalized to a large variety of information gathering tasks.

show abstract

“…The kinetic equation is easily expressed as a quadratic univariate equation of time or

. In another study, a robotic agent is designed to reach an unknown target ( Ramamurthy et al., 2019 ). The solid body property enforces a linear relationship of segments, which serves as a regularizer in the policy architectures.…”

Section: Knowledge and Its Representationsmentioning

confidence: 99%

Integrating Machine Learning with Human Knowledge

et al. 2020

View full text Add to dashboard Cite

Summary Machine learning has been heavily researched and widely used in many disciplines. However, achieving high accuracy requires a large amount of data that is sometimes difficult, expensive, or impractical to obtain. Integrating human knowledge into machine learning can significantly reduce data requirement, increase reliability and robustness of machine learning, and build explainable machine learning systems. This allows leveraging the vast amount of human knowledge and capability of machine learning to achieve functions and performance not available before and will facilitate the interaction between human beings and machine learning systems, making machine learning decisions understandable to humans. This paper gives an overview of the knowledge and its representations that can be integrated into machine learning and the methodology. We cover the fundamentals, current status, and recent progress of the methods, with a focus on popular and new topics. The perspectives on future directions are also discussed.

show abstract

Leveraging Domain Knowledge for Reinforcement Learning Using MMC Architectures

Cited by 12 publications

References 17 publications

Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems

Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems

Robotic Information Gathering With Reinforcement Learning Assisted by Domain Knowledge: An Application to Gas Source Localization

Integrating Machine Learning with Human Knowledge

Contact Info

Product

Resources

About